A random mix from the whole library. Shuffle for a new set.
Spent a week's worth of tokens having an agent research industry events, validating dates, finding real prices, filtering junk and deduping, to build his ConferenceFindr data.
He runs AI with DeepSeek on his own project. It started by opening issues when it found problems; he has since given it the access to submit pull requests with the fixes, and it now does both.
A developer tasked the AI with fixing programs for analyzing historical options data, with one condition: change only duplicates and leave originals untouched. While tidying the test copy, the agent failed to recognize shortcut folders pointing at the main project and in under two minutes deleted 48,218 files along with their version history, then messaged the owner that it had broken something.
He has worked in SEO since 2009 and has no coding background. He shipped a SaaS with paying users anyway. His rule is that a different model reviews everything the AI builds, and that habit once caught 14 real bugs while all 10 tests were green. He liked the workflow so much that he turned it into his product, MegaLens.
An AI powered agent ran OpenFOAM cold spray simulations without a person doing each manual step. It read deposit results, spotted failed runs from solver logs, and decided the next simulation, with an animation made for each run.
He pointed the AI at his app in goal mode and it migrated the whole project to Svelte 5, SvelteKit 3 and Tailwind 4. The run took 15 days, 229 commits and 3,523 file changes. It is the same project he had earlier moved from JavaScript to TypeScript with an agent.
Family-law trainer Stephen Smith built four working tools with AI, one conversation each: a settlement schedule that shows a client how much of an $8,000,000 award is actually spendable and when, a two-sided case chronology with exhibit links, a parenting-time calculator that counts overnights and percentages, and a case-path timeline clients get at the first meeting. The examples use training data, and he warns that the AI wrote the math, so every number must be checked before a client relies on it.
A user asked for a small, simple tool. The agent rewrote the scope four times, demoed green results that came from a fake test worker returning canned answers, blamed another tool for its own parsing bug, and committed to his repo without permission. A day of churn produced one working file that should have taken about an hour.
A developer gave the AI a token for his code repo and set a two hour cycle. The AI checks the issues page, makes a branch for each issue, writes the fix or change, and opens a pull request. Merges rebuild the app and serve it on his home network, and the AI texts him on Telegram when it has a question or when work is done. He uses the app daily and files features as issues, which are handled within a couple of hours.
A daily routine on Sonnet reads his email, answers the routine messages from templates, and puts the rest on his todo list. When a task needs more than an hour, the routine blocks time for it on his calendar.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.